CtrlK
BlogDocsLog inGet started
Tessl Logo

ux-disruptivo

Use when designing new screens, redesigning existing UI, creating visual concepts, or improving interfaces in Nicolify. Executes a 7-phase creative Design Thinking workflow: defines user personas, frames problems, audits existing components (Shadcn UI + Tailwind CSS v4 + FSD architecture), researches SaaS UI patterns, proposes multiple distinct layout paradigms with ASCII wireframes and HTML mockups, iterates through dialogue, and delivers a complete UI-SPEC.md with component trees, data flow, responsive behavior, and interaction patterns — all following Nicolify's design tokens and codebase conventions. Triggers: 'diseña', 'rediseña', 'nueva pantalla', 'concepto visual', 'propuesta de diseño', 'UX', 'layout', 'prototipo', 'mejora la interfaz', 'wireframe', 'mockup', 'esquema de color', 'componentes de pantalla'.

72

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

77%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured multi-phase workflow with explicit gates, validation, feedback loops, and properly externalized reference files. Its main weakness is redundancy between the Quick Reference, per-phase instructions, and the Common Mistakes table, which inflates the token budget without adding new guidance.

Suggestions

Collapse the 'Common Mistakes' table into inline callouts only where a mistake is not already covered by a phase rule, to remove restated content like the one-layout-per-proposal and verify-Shadcn rules.

Provide a minimal copy-paste tailwind.config snippet for the HTML preview's token replication step rather than describing it abstractly.

Trim the per-phase 'Tools:' lines now that the Quick Reference table already maps each phase to its tools.

DimensionReasoningScore

Conciseness

Mostly efficient and free of basic-concept explanations, but the 'Common Mistakes' table restates rules already given in the phases (e.g., one-layout-per-proposal, verify installed Shadcn components) and the Quick Reference plus per-phase tool lines overlap, so it could be tightened — the level-3 anchor rather than the minor-trim level-4.

3 / 5

Actionability

Gives concrete, executable guidance — specific Glob/Grep patterns ('frontend/src/components/ui/*.tsx'), exact questions to ask, and step-by-step HTML-preview instructions — with only minor gaps; not level 5 because some steps (e.g., tailwind.config token replication) are described rather than given as copy-paste ready snippets.

4 / 5

Workflow Clarity

The 7 phases are clearly sequenced with an explicit gate ('Do NOT proceed to Phase 2 without answers to at least questions 1 and 2'), a validation checkpoint in Phase 7 ('Verify real component names against codebase' before writing), and feedback loops in Phase 6 (iterate until confirmation, 'volvamos a [phase]' re-entry) plus an Edge Cases table — matching the level-5 anchor.

5 / 5

Progressive Disclosure

The body is an overview that signals one-level-deep references loaded on demand (design-system-inventory.md, proposal-format.md, ascii-mockup-guide.md, ui-spec-template.md, research-prompts.md), all of which exist in references/ and are cited at their point of use — the level-5 'clear overview, well-signaled one-level references' anchor.

5 / 5

Total

17

/

20

Passed

Description

100%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, third-person description that explicitly states capabilities, when to use the skill, and a rich set of natural trigger terms, all scoped to a distinct Nicolify niche. It is somewhat long but every clause carries concrete content rather than fluff.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'defines user personas, frames problems, audits existing components', 'proposes multiple distinct layout paradigms with ASCII wireframes and HTML mockups', 'delivers a complete UI-SPEC.md with component trees, data flow, responsive behavior' — with comprehensive coverage, matching the level-5 anchor rather than the minor-gaps level-4.

5 / 5

Completeness

Explicitly answers both 'what' (the 7-phase workflow and its deliverables) and 'when' ('Use when designing new screens, redesigning existing UI…' plus the Triggers list), with concrete trigger phrases — the level-5 anchor.

5 / 5

Trigger Term Quality

An explicit 'Triggers:' block supplies natural Spanish phrases a founder would say ('diseña', 'rediseña', 'nueva pantalla', 'prototipo', 'wireframe', 'mockup', 'esquema de color') plus synonyms, matching comprehensive coverage with variations; not level 4 because common variations are well covered.

5 / 5

Distinctiveness Conflict Risk

Scoped to 'Nicolify' with its design tokens, Shadcn/Tailwind v4/FSD stack, and Spanish triggers, and explicitly distinguishes itself from the mechanical 'nicolify-ux-designer' — a clear niche with minimal conflict risk.

5 / 5

Total

20

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
alpacapurpura/luana-method
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.